Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     peque
    -0.07
     vieux
    -0.07
    ество
    -0.06
     сот
    -0.06
    _KEYS
    -0.06
    (set
    -0.06
    348
    -0.06
     pequ
    -0.06
     sweating
    -0.06
    VG
    -0.06
    POSITIVE LOGITS
     Every
    0.07
    Every
    0.07
    _flow
    0.06
    avigate
    0.06
    liğinde
    0.06
    ी↵
    0.06
     okul
    0.06
    střed
    0.06
    .Receive
    0.05
     dav
    0.05
    Act Density 0.008%

    No Known Activations